mlsanityData to 7 Oct 2026

Dense Unsupervised Learning for Video Segmentation

arXiv 2111.06265 ↗First posted 11 Nov 2021cs.CV cs.LGcited by 26

Not on the map. Why?

Abstract (arXiv)

We present a novel approach to unsupervised learning for video object segmentation (VOS). Unlike previous work, our formulation allows to learn dense feature representations directly in a fully convolutional regime. We rely on uniform grid sampling to extract a set of anchors and train our model to disambiguate between them on both inter- and intra-video levels. However, a naive scheme to train such a model results in a degenerate solution. We propose to prevent this with a simple regularisation scheme, accommodating the equivariance property of the segmentation task to similarity transformations. Our training objective admits efficient implementation and exhibits fast training convergence. On established VOS benchmarks, our approach exceeds the segmentation accuracy of previous work despite using significantly less training data and compute power.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 46 of its 50 references that are in the map. First posted on arXiv 11 Nov 2021.

Builds on

46 of 50 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2016Layer Normalizationcited by 5,579
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  9. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  10. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  11. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  12. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
34 more
  1. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  2. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  3. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  4. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 806
  5. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 672
  6. 2017Time-Contrastive Networks: Self-Supervised Learning from Videocited by 453
  7. 2019Video Object Segmentation using Space-Time Memory Networkscited by 436
  8. 2020Spatiotemporal Contrastive Video Representation Learningcited by 372
  9. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 368
  10. 2018TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wildcited by 342
  11. 2020Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentationcited by 299
  12. 2019Learning Correspondence from the Cycle-Consistency of Timecited by 269
  13. 2020Space-Time Correspondence as a Contrastive Random Walkcited by 239
  14. 2016One-Shot Video Object Segmentationcited by 233
  15. 2020Self-supervised Co-training for Video Representation Learningcited by 232
  16. 2018YouTube-VOS: Sequence-to-Sequence Video Object Segmentationcited by 228
  17. 2021A Large-Scale Study on Unsupervised Spatiotemporal Representation Learningcited by 214
  18. 2017UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Losscited by 202
  19. 2018Why do deep convolutional networks generalize so poorly to small image transformations?cited by 198
  20. 2018Tracking Emerges by Colorizing Videoscited by 166
  21. 2021Self-supervised Augmentation Consistency for Adapting Semantic Segmentationcited by 149
  22. 2020Unsupervised Learning of Dense Visual Representationscited by 147
  23. 2016Learning Features by Watching Objects Movecited by 138
  24. 2021TCLR: Temporal Contrastive Learning for Video Representationcited by 136
  25. 2019Pixel-Adaptive Convolutional Neural Networkscited by 126
  26. 2020MAST: A Memory-Augmented Self-supervised Trackercited by 109
  27. 2019SCOPS: Self-Supervised Co-Part Segmentationcited by 100
  28. 2018PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentationcited by 81
  29. 2019Joint-task Self-supervised Learning for Temporal Correspondencecited by 80
  30. 2018Long-term Tracking in the Wild: A Benchmarkcited by 55
  31. 2021Self-Supervised Representation Learning from Flow Equivariancecited by 28
  32. 2020Can Temporal Information Help with Contrastive Self-Supervised Learning?cited by 27
  33. 2019Self-supervised Learning for Video Correspondence Flowcited by 21
  34. 2020Contrastive Transformation for Self-supervised Correspondence Learningcited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 10; 2024: 4; 2025: 4; 2026: 2.

26 papers.

Sort:

  1. 2023A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyondcited by 55
  2. 2023Advances in Deep Concealed Scene Understandingcited by 47
  3. 2023Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representationscited by 35
  4. 2023DropMAE: Learning Representations via Masked Autoencoders with Spatial-Attention Dropout for Temporal Matching Taskscited by 22
  5. 2023Boosting Video Object Segmentation via Space-time Correspondence Learningcited by 21
  6. 2023Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentationcited by 16
  7. 2024Near, far: Patch-ordering enhances vision foundation models' scene understandingcited by 15
  8. 2023UVOSAM: A Mask-free Paradigm for Unsupervised Video Object Segmentation via Segment Anything Modelcited by 14
  9. 2022Spatial-then-Temporal Self-Supervised Learning for Video Correspondencecited by 13
  10. 2022Demystifying Unsupervised Semantic Correspondence Estimationcited by 9
  11. 2022In-N-Out Generative Learning for Dense Unsupervised Video Segmentationcited by 7
  12. 2022Transfer of Representations to Video Label Propagation: Implementation Factors Mattercited by 5
14 more
  1. 2025MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learningcited by 5
  2. 2023Learning Fine-Grained Features for Pixel-wise Video Correspondencescited by 4
  3. 2023Unsupervised CD in satellite image time series by contrastive learning and feature trackingcited by 3
  4. 2022Overcoming Annotation Bottlenecks in Underwater Fish Segmentation: A Robust Self-Supervised Learning Approachcited by 2
  5. 2023MomentaMorph: Unsupervised Spatial-Temporal Registration with Momenta, Shooting, and Correctioncited by 2
  6. 2024Unsupervised Cognitioncited by 2
  7. 2025FlowFeat: Pixel-Dense Embedding of Motion Profilescited by 2
  8. 2022How to Track and Segment Fish without Human Annotations: A Self-Supervised Deep Learning Approachcited by 1
  9. 2025AutoQ-VIS: Improving Unsupervised Video Instance Segmentation via Automatic Quality Assessmentcited by 1
  10. 2024Dynamic in Static: Hybrid Visual Correspondence for Self-Supervised Video Object Segmentationcited by 0
  11. 2024One-shot Training for Video Object Segmentationcited by 0
  12. 2025Boosting Unsupervised Video Instance Segmentation with Automatic Quality-Guided Self-Trainingcited by 0
  13. 2026Featurising Pixels from Dynamic 3D Scenes with Linear In-Context Learnerscited by 0
  14. 2026`Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentationcited by 0